Deep Learning for Predictive Analytics in Reversible Steganography

DOI DOI PDF 参考文献62件 オープンアクセス
  • Ching-Chun Chang
    National Institute of Informatics, Tokyo, Japan
  • Xu Wang
    Department of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan
  • Sisheng Chen
    Department of Information Engineering and Computer Science, Feng Chia University, Taichung, Taiwan
  • Victor Sanchez
    Department of Computer Science, University of Warwick, Coventry, U.K.
  • Isao Echizen
    National Institute of Informatics, Tokyo, Japan
  • Chang-Tsun Li
    School of Information Technology, Deakin University, Geelong, VIC, Australia

書誌事項

公開日
2023
資源種別
journal article
権利情報
  • https://creativecommons.org/licenses/by/4.0/legalcode
DOI
  • 10.1109/access.2023.3233976
  • 10.48550/arxiv.2106.06924
公開者
Institute of Electrical and Electronics Engineers (IEEE)

説明

Deep learning is regarded as a promising solution for reversible steganography. There is an accelerating trend of representing a reversible steo-system by monolithic neural networks, which bypass intermediate operations in traditional pipelines of reversible steganography. This end-to-end paradigm, however, suffers from imperfect reversibility. By contrast, the modular paradigm that incorporates neural networks into modules of traditional pipelines can stably guarantee reversibility with mathematical explainability. Prediction-error modulation is a well-established reversible steganography pipeline for digital images. It consists of a predictive analytics module and a reversible coding module. Given that reversibility is governed independently by the coding module, we narrow our focus to the incorporation of neural networks into the analytics module, which serves the purpose of predicting pixel intensities and a pivotal role in determining capacity and imperceptibility. The objective of this study is to evaluate the impacts of different training configurations upon predictive accuracy of neural networks and provide practical insights. In particular, we investigate how different initialisation strategies for input images may affect the learning process and how different training strategies for dual-layer prediction respond to the problem of distributional shift. Furthermore, we compare steganographic performance of various model architectures with different loss functions.

収録刊行物

  • IEEE Access

    IEEE Access 11 3494-3510, 2023

    Institute of Electrical and Electronics Engineers (IEEE)

参考文献 (62)*注記

もっと見る

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ